423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-15 08:08:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix SFT trainer

Browse Source 
Former-commit-id: bf09b6a6cd75cc2738d9af6b8c30bcbba77fa9b5
This commit is contained in:
hiyouga 2023-10-31 21:52:52 +08:00
parent db06fcfc84
commit 2406200914
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/tuner/sft/trainer.py
View File

@ -33,10 +33,10 @@ class CustomSeq2SeqTrainer(Seq2SeqTrainer):
Subclass and override to inject custom behavior. Subclass and override to inject custom behavior.
""" """
labels = inputs["labels"].clone() if "labels" in inputs else None # backup labels
if self.args.predict_with_generate: if self.args.predict_with_generate:
assert self.tokenizer.padding_side == "left", "This method only accepts left-padded tensor." assert self.tokenizer.padding_side == "left", "This method only accepts left-padded tensor."
prompt_len, label_len = inputs["input_ids"].size(-1), inputs["labels"].size(-1) prompt_len, label_len = inputs["input_ids"].size(-1), inputs["labels"].size(-1)
labels = inputs["labels"].clone()
if prompt_len > label_len: if prompt_len > label_len:
inputs["labels"] = self._pad_tensors_to_target_len(inputs["labels"], inputs["input_ids"]) inputs["labels"] = self._pad_tensors_to_target_len(inputs["labels"], inputs["input_ids"])
if label_len > prompt_len: if label_len > prompt_len: